steveloughran commented on a change in pull request #1830: HADOOP-11867: Add
gather API to file system.
URL: https://github.com/apache/hadoop/pull/1830#discussion_r374651071
##########
File path:
hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/ChecksumFileSystem.java
##########
@@ -261,15 +270,129 @@ protected int readChunk(long pos, byte[] buf, int
offset, int len,
len = Math.min(len, bytesPerSum * (sumLenRead / CHECKSUM_SIZE));
}
}
- if(pos != datas.getPos()) {
+ if (pos != datas.getPos()) {
datas.seek(pos);
}
int nread = readFully(datas, buf, offset, len);
if (eof && nread > 0) {
- throw new ChecksumException("Checksum error: "+file+" at "+pos, pos);
+ throw new ChecksumException("Checksum error: " + file + " at " + pos,
pos);
}
return nread;
}
+
+ public static long findChecksumOffset(long dataOffset,
+ int bytesPerSum) {
+ return HEADER_LENGTH + (dataOffset/bytesPerSum) *
FSInputChecker.CHECKSUM_SIZE;
+ }
+
+ /**
+ * Find the checksum ranges that correspond to the given data ranges.
Review comment:
be nice to explain why this is needed, for those of us who don't normally go
near this file
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
